Model save
Browse files- README.md +58 -0
- all_results.json +8 -0
- config.json +35 -0
- generation_config.json +10 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +650 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +130 -0
- train_results.json +8 -0
- trainer_state.json +706 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: tiiuae/falcon-mamba-7b-instruct
|
3 |
+
library_name: transformers
|
4 |
+
model_name: mamba-distill-7b
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
- trl
|
8 |
+
- sft
|
9 |
+
licence: license
|
10 |
+
---
|
11 |
+
|
12 |
+
# Model Card for mamba-distill-7b
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [tiiuae/falcon-mamba-7b-instruct](https://huggingface.co/tiiuae/falcon-mamba-7b-instruct).
|
15 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
16 |
+
|
17 |
+
## Quick start
|
18 |
+
|
19 |
+
```python
|
20 |
+
from transformers import pipeline
|
21 |
+
|
22 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
23 |
+
generator = pipeline("text-generation", model="KotshinZ/mamba-distill-7b", device="cuda")
|
24 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
25 |
+
print(output["generated_text"])
|
26 |
+
```
|
27 |
+
|
28 |
+
## Training procedure
|
29 |
+
|
30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/shin2021001-osaka-city-university/huggingface/runs/fw25pcxt)
|
31 |
+
|
32 |
+
|
33 |
+
This model was trained with SFT.
|
34 |
+
|
35 |
+
### Framework versions
|
36 |
+
|
37 |
+
- TRL: 0.15.2
|
38 |
+
- Transformers: 4.50.1
|
39 |
+
- Pytorch: 2.5.1
|
40 |
+
- Datasets: 3.4.1
|
41 |
+
- Tokenizers: 0.21.1
|
42 |
+
|
43 |
+
## Citations
|
44 |
+
|
45 |
+
|
46 |
+
|
47 |
+
Cite TRL as:
|
48 |
+
|
49 |
+
```bibtex
|
50 |
+
@misc{vonwerra2022trl,
|
51 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
52 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
|
53 |
+
year = 2020,
|
54 |
+
journal = {GitHub repository},
|
55 |
+
publisher = {GitHub},
|
56 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
57 |
+
}
|
58 |
+
```
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"total_flos": 3.616227566899167e+18,
|
3 |
+
"train_loss": 16.595592213948567,
|
4 |
+
"train_runtime": 29081.677,
|
5 |
+
"train_samples": 16610,
|
6 |
+
"train_samples_per_second": 0.827,
|
7 |
+
"train_steps_per_second": 0.013
|
8 |
+
}
|
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"FalconMambaForCausalLM"
|
4 |
+
],
|
5 |
+
"bos_token_id": 8,
|
6 |
+
"conv_kernel": 4,
|
7 |
+
"eos_token_id": 11,
|
8 |
+
"expand": 16,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.1,
|
12 |
+
"intermediate_size": 8192,
|
13 |
+
"layer_norm_epsilon": 1e-05,
|
14 |
+
"mixer_rms_eps": 1e-06,
|
15 |
+
"model_type": "falcon_mamba",
|
16 |
+
"num_hidden_layers": 64,
|
17 |
+
"pad_token_id": 0,
|
18 |
+
"rescale_prenorm_residual": false,
|
19 |
+
"residual_in_fp32": true,
|
20 |
+
"state_size": 16,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"time_step_floor": 0.0001,
|
23 |
+
"time_step_init_scheme": "random",
|
24 |
+
"time_step_max": 0.1,
|
25 |
+
"time_step_min": 0.001,
|
26 |
+
"time_step_rank": 256,
|
27 |
+
"time_step_scale": 1.0,
|
28 |
+
"torch_dtype": "bfloat16",
|
29 |
+
"transformers_version": "4.50.1",
|
30 |
+
"use_bias": false,
|
31 |
+
"use_cache": false,
|
32 |
+
"use_conv_bias": true,
|
33 |
+
"use_mambapy": false,
|
34 |
+
"vocab_size": 65024
|
35 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 8,
|
4 |
+
"eos_token_id": [
|
5 |
+
11,
|
6 |
+
10
|
7 |
+
],
|
8 |
+
"pad_token_id": 0,
|
9 |
+
"transformers_version": "4.50.1"
|
10 |
+
}
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f39e223c48d308387ded14110ce989bb372db7277cbef5daec20cfa023cc66f
|
3 |
+
size 4956184024
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbed912f504bd39d4172e756af4817868189b6eba210d502da3facec29aececa
|
3 |
+
size 4987536920
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f1bd09a9aefbd68a9dddd0763450beb3c785ce39c9c29a98a0b3753adc9d5b6
|
3 |
+
size 4601680888
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,650 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 14545330176
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"backbone.embeddings.weight": "model-00001-of-00003.safetensors",
|
7 |
+
"backbone.layers.0.mixer.A_log": "model-00001-of-00003.safetensors",
|
8 |
+
"backbone.layers.0.mixer.D": "model-00001-of-00003.safetensors",
|
9 |
+
"backbone.layers.0.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
10 |
+
"backbone.layers.0.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
11 |
+
"backbone.layers.0.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
12 |
+
"backbone.layers.0.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
13 |
+
"backbone.layers.0.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
14 |
+
"backbone.layers.0.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
15 |
+
"backbone.layers.0.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
16 |
+
"backbone.layers.0.norm.weight": "model-00001-of-00003.safetensors",
|
17 |
+
"backbone.layers.1.mixer.A_log": "model-00001-of-00003.safetensors",
|
18 |
+
"backbone.layers.1.mixer.D": "model-00001-of-00003.safetensors",
|
19 |
+
"backbone.layers.1.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
20 |
+
"backbone.layers.1.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
21 |
+
"backbone.layers.1.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
22 |
+
"backbone.layers.1.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
23 |
+
"backbone.layers.1.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
24 |
+
"backbone.layers.1.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
25 |
+
"backbone.layers.1.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
26 |
+
"backbone.layers.1.norm.weight": "model-00001-of-00003.safetensors",
|
27 |
+
"backbone.layers.10.mixer.A_log": "model-00001-of-00003.safetensors",
|
28 |
+
"backbone.layers.10.mixer.D": "model-00001-of-00003.safetensors",
|
29 |
+
"backbone.layers.10.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
30 |
+
"backbone.layers.10.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
31 |
+
"backbone.layers.10.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
32 |
+
"backbone.layers.10.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
33 |
+
"backbone.layers.10.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
34 |
+
"backbone.layers.10.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
35 |
+
"backbone.layers.10.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
36 |
+
"backbone.layers.10.norm.weight": "model-00001-of-00003.safetensors",
|
37 |
+
"backbone.layers.11.mixer.A_log": "model-00001-of-00003.safetensors",
|
38 |
+
"backbone.layers.11.mixer.D": "model-00001-of-00003.safetensors",
|
39 |
+
"backbone.layers.11.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
40 |
+
"backbone.layers.11.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
41 |
+
"backbone.layers.11.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
42 |
+
"backbone.layers.11.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
43 |
+
"backbone.layers.11.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
44 |
+
"backbone.layers.11.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
45 |
+
"backbone.layers.11.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
46 |
+
"backbone.layers.11.norm.weight": "model-00001-of-00003.safetensors",
|
47 |
+
"backbone.layers.12.mixer.A_log": "model-00001-of-00003.safetensors",
|
48 |
+
"backbone.layers.12.mixer.D": "model-00001-of-00003.safetensors",
|
49 |
+
"backbone.layers.12.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
50 |
+
"backbone.layers.12.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
51 |
+
"backbone.layers.12.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
52 |
+
"backbone.layers.12.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
53 |
+
"backbone.layers.12.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
54 |
+
"backbone.layers.12.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
55 |
+
"backbone.layers.12.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
56 |
+
"backbone.layers.12.norm.weight": "model-00001-of-00003.safetensors",
|
57 |
+
"backbone.layers.13.mixer.A_log": "model-00001-of-00003.safetensors",
|
58 |
+
"backbone.layers.13.mixer.D": "model-00001-of-00003.safetensors",
|
59 |
+
"backbone.layers.13.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
60 |
+
"backbone.layers.13.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
61 |
+
"backbone.layers.13.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
62 |
+
"backbone.layers.13.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
63 |
+
"backbone.layers.13.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
64 |
+
"backbone.layers.13.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
65 |
+
"backbone.layers.13.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
66 |
+
"backbone.layers.13.norm.weight": "model-00001-of-00003.safetensors",
|
67 |
+
"backbone.layers.14.mixer.A_log": "model-00001-of-00003.safetensors",
|
68 |
+
"backbone.layers.14.mixer.D": "model-00001-of-00003.safetensors",
|
69 |
+
"backbone.layers.14.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
70 |
+
"backbone.layers.14.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
71 |
+
"backbone.layers.14.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
72 |
+
"backbone.layers.14.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
73 |
+
"backbone.layers.14.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
74 |
+
"backbone.layers.14.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
75 |
+
"backbone.layers.14.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
76 |
+
"backbone.layers.14.norm.weight": "model-00001-of-00003.safetensors",
|
77 |
+
"backbone.layers.15.mixer.A_log": "model-00001-of-00003.safetensors",
|
78 |
+
"backbone.layers.15.mixer.D": "model-00001-of-00003.safetensors",
|
79 |
+
"backbone.layers.15.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
80 |
+
"backbone.layers.15.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
81 |
+
"backbone.layers.15.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
82 |
+
"backbone.layers.15.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
83 |
+
"backbone.layers.15.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
84 |
+
"backbone.layers.15.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
85 |
+
"backbone.layers.15.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
86 |
+
"backbone.layers.15.norm.weight": "model-00001-of-00003.safetensors",
|
87 |
+
"backbone.layers.16.mixer.A_log": "model-00001-of-00003.safetensors",
|
88 |
+
"backbone.layers.16.mixer.D": "model-00001-of-00003.safetensors",
|
89 |
+
"backbone.layers.16.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
90 |
+
"backbone.layers.16.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
91 |
+
"backbone.layers.16.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
92 |
+
"backbone.layers.16.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
93 |
+
"backbone.layers.16.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
94 |
+
"backbone.layers.16.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
95 |
+
"backbone.layers.16.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
96 |
+
"backbone.layers.16.norm.weight": "model-00001-of-00003.safetensors",
|
97 |
+
"backbone.layers.17.mixer.A_log": "model-00001-of-00003.safetensors",
|
98 |
+
"backbone.layers.17.mixer.D": "model-00001-of-00003.safetensors",
|
99 |
+
"backbone.layers.17.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
100 |
+
"backbone.layers.17.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
101 |
+
"backbone.layers.17.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
102 |
+
"backbone.layers.17.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
103 |
+
"backbone.layers.17.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
104 |
+
"backbone.layers.17.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
105 |
+
"backbone.layers.17.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
106 |
+
"backbone.layers.17.norm.weight": "model-00001-of-00003.safetensors",
|
107 |
+
"backbone.layers.18.mixer.A_log": "model-00001-of-00003.safetensors",
|
108 |
+
"backbone.layers.18.mixer.D": "model-00001-of-00003.safetensors",
|
109 |
+
"backbone.layers.18.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
110 |
+
"backbone.layers.18.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
111 |
+
"backbone.layers.18.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
112 |
+
"backbone.layers.18.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
113 |
+
"backbone.layers.18.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
114 |
+
"backbone.layers.18.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
115 |
+
"backbone.layers.18.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
116 |
+
"backbone.layers.18.norm.weight": "model-00001-of-00003.safetensors",
|
117 |
+
"backbone.layers.19.mixer.A_log": "model-00001-of-00003.safetensors",
|
118 |
+
"backbone.layers.19.mixer.D": "model-00001-of-00003.safetensors",
|
119 |
+
"backbone.layers.19.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
120 |
+
"backbone.layers.19.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
121 |
+
"backbone.layers.19.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
122 |
+
"backbone.layers.19.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
123 |
+
"backbone.layers.19.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
124 |
+
"backbone.layers.19.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
125 |
+
"backbone.layers.19.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
126 |
+
"backbone.layers.19.norm.weight": "model-00001-of-00003.safetensors",
|
127 |
+
"backbone.layers.2.mixer.A_log": "model-00001-of-00003.safetensors",
|
128 |
+
"backbone.layers.2.mixer.D": "model-00001-of-00003.safetensors",
|
129 |
+
"backbone.layers.2.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
130 |
+
"backbone.layers.2.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
131 |
+
"backbone.layers.2.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
132 |
+
"backbone.layers.2.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
133 |
+
"backbone.layers.2.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
134 |
+
"backbone.layers.2.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
135 |
+
"backbone.layers.2.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
136 |
+
"backbone.layers.2.norm.weight": "model-00001-of-00003.safetensors",
|
137 |
+
"backbone.layers.20.mixer.A_log": "model-00001-of-00003.safetensors",
|
138 |
+
"backbone.layers.20.mixer.D": "model-00001-of-00003.safetensors",
|
139 |
+
"backbone.layers.20.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
140 |
+
"backbone.layers.20.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
141 |
+
"backbone.layers.20.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
142 |
+
"backbone.layers.20.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
143 |
+
"backbone.layers.20.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
144 |
+
"backbone.layers.20.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
145 |
+
"backbone.layers.20.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
146 |
+
"backbone.layers.20.norm.weight": "model-00001-of-00003.safetensors",
|
147 |
+
"backbone.layers.21.mixer.A_log": "model-00001-of-00003.safetensors",
|
148 |
+
"backbone.layers.21.mixer.D": "model-00001-of-00003.safetensors",
|
149 |
+
"backbone.layers.21.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
150 |
+
"backbone.layers.21.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
151 |
+
"backbone.layers.21.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
152 |
+
"backbone.layers.21.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
153 |
+
"backbone.layers.21.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
154 |
+
"backbone.layers.21.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
155 |
+
"backbone.layers.21.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
156 |
+
"backbone.layers.21.norm.weight": "model-00001-of-00003.safetensors",
|
157 |
+
"backbone.layers.22.mixer.A_log": "model-00002-of-00003.safetensors",
|
158 |
+
"backbone.layers.22.mixer.D": "model-00002-of-00003.safetensors",
|
159 |
+
"backbone.layers.22.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
160 |
+
"backbone.layers.22.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
161 |
+
"backbone.layers.22.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
162 |
+
"backbone.layers.22.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
163 |
+
"backbone.layers.22.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
164 |
+
"backbone.layers.22.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
165 |
+
"backbone.layers.22.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
166 |
+
"backbone.layers.22.norm.weight": "model-00002-of-00003.safetensors",
|
167 |
+
"backbone.layers.23.mixer.A_log": "model-00002-of-00003.safetensors",
|
168 |
+
"backbone.layers.23.mixer.D": "model-00002-of-00003.safetensors",
|
169 |
+
"backbone.layers.23.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
170 |
+
"backbone.layers.23.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
171 |
+
"backbone.layers.23.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
172 |
+
"backbone.layers.23.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
173 |
+
"backbone.layers.23.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
174 |
+
"backbone.layers.23.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
175 |
+
"backbone.layers.23.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
176 |
+
"backbone.layers.23.norm.weight": "model-00002-of-00003.safetensors",
|
177 |
+
"backbone.layers.24.mixer.A_log": "model-00002-of-00003.safetensors",
|
178 |
+
"backbone.layers.24.mixer.D": "model-00002-of-00003.safetensors",
|
179 |
+
"backbone.layers.24.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
180 |
+
"backbone.layers.24.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
181 |
+
"backbone.layers.24.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
182 |
+
"backbone.layers.24.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
183 |
+
"backbone.layers.24.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
184 |
+
"backbone.layers.24.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
185 |
+
"backbone.layers.24.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
186 |
+
"backbone.layers.24.norm.weight": "model-00002-of-00003.safetensors",
|
187 |
+
"backbone.layers.25.mixer.A_log": "model-00002-of-00003.safetensors",
|
188 |
+
"backbone.layers.25.mixer.D": "model-00002-of-00003.safetensors",
|
189 |
+
"backbone.layers.25.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
190 |
+
"backbone.layers.25.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
191 |
+
"backbone.layers.25.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
192 |
+
"backbone.layers.25.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
193 |
+
"backbone.layers.25.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
194 |
+
"backbone.layers.25.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
195 |
+
"backbone.layers.25.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
196 |
+
"backbone.layers.25.norm.weight": "model-00002-of-00003.safetensors",
|
197 |
+
"backbone.layers.26.mixer.A_log": "model-00002-of-00003.safetensors",
|
198 |
+
"backbone.layers.26.mixer.D": "model-00002-of-00003.safetensors",
|
199 |
+
"backbone.layers.26.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
200 |
+
"backbone.layers.26.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
201 |
+
"backbone.layers.26.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
202 |
+
"backbone.layers.26.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
203 |
+
"backbone.layers.26.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
204 |
+
"backbone.layers.26.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
205 |
+
"backbone.layers.26.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
206 |
+
"backbone.layers.26.norm.weight": "model-00002-of-00003.safetensors",
|
207 |
+
"backbone.layers.27.mixer.A_log": "model-00002-of-00003.safetensors",
|
208 |
+
"backbone.layers.27.mixer.D": "model-00002-of-00003.safetensors",
|
209 |
+
"backbone.layers.27.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
210 |
+
"backbone.layers.27.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
211 |
+
"backbone.layers.27.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
212 |
+
"backbone.layers.27.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
213 |
+
"backbone.layers.27.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
214 |
+
"backbone.layers.27.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
215 |
+
"backbone.layers.27.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
216 |
+
"backbone.layers.27.norm.weight": "model-00002-of-00003.safetensors",
|
217 |
+
"backbone.layers.28.mixer.A_log": "model-00002-of-00003.safetensors",
|
218 |
+
"backbone.layers.28.mixer.D": "model-00002-of-00003.safetensors",
|
219 |
+
"backbone.layers.28.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
220 |
+
"backbone.layers.28.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
221 |
+
"backbone.layers.28.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
222 |
+
"backbone.layers.28.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
223 |
+
"backbone.layers.28.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
224 |
+
"backbone.layers.28.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
225 |
+
"backbone.layers.28.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
226 |
+
"backbone.layers.28.norm.weight": "model-00002-of-00003.safetensors",
|
227 |
+
"backbone.layers.29.mixer.A_log": "model-00002-of-00003.safetensors",
|
228 |
+
"backbone.layers.29.mixer.D": "model-00002-of-00003.safetensors",
|
229 |
+
"backbone.layers.29.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
230 |
+
"backbone.layers.29.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
231 |
+
"backbone.layers.29.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
232 |
+
"backbone.layers.29.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
233 |
+
"backbone.layers.29.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
234 |
+
"backbone.layers.29.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
235 |
+
"backbone.layers.29.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
236 |
+
"backbone.layers.29.norm.weight": "model-00002-of-00003.safetensors",
|
237 |
+
"backbone.layers.3.mixer.A_log": "model-00001-of-00003.safetensors",
|
238 |
+
"backbone.layers.3.mixer.D": "model-00001-of-00003.safetensors",
|
239 |
+
"backbone.layers.3.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
240 |
+
"backbone.layers.3.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
241 |
+
"backbone.layers.3.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
242 |
+
"backbone.layers.3.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
243 |
+
"backbone.layers.3.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
244 |
+
"backbone.layers.3.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
245 |
+
"backbone.layers.3.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
246 |
+
"backbone.layers.3.norm.weight": "model-00001-of-00003.safetensors",
|
247 |
+
"backbone.layers.30.mixer.A_log": "model-00002-of-00003.safetensors",
|
248 |
+
"backbone.layers.30.mixer.D": "model-00002-of-00003.safetensors",
|
249 |
+
"backbone.layers.30.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
250 |
+
"backbone.layers.30.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
251 |
+
"backbone.layers.30.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
252 |
+
"backbone.layers.30.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
253 |
+
"backbone.layers.30.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
254 |
+
"backbone.layers.30.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
255 |
+
"backbone.layers.30.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
256 |
+
"backbone.layers.30.norm.weight": "model-00002-of-00003.safetensors",
|
257 |
+
"backbone.layers.31.mixer.A_log": "model-00002-of-00003.safetensors",
|
258 |
+
"backbone.layers.31.mixer.D": "model-00002-of-00003.safetensors",
|
259 |
+
"backbone.layers.31.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
260 |
+
"backbone.layers.31.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
261 |
+
"backbone.layers.31.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
262 |
+
"backbone.layers.31.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
263 |
+
"backbone.layers.31.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
264 |
+
"backbone.layers.31.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
265 |
+
"backbone.layers.31.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
266 |
+
"backbone.layers.31.norm.weight": "model-00002-of-00003.safetensors",
|
267 |
+
"backbone.layers.32.mixer.A_log": "model-00002-of-00003.safetensors",
|
268 |
+
"backbone.layers.32.mixer.D": "model-00002-of-00003.safetensors",
|
269 |
+
"backbone.layers.32.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
270 |
+
"backbone.layers.32.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
271 |
+
"backbone.layers.32.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
272 |
+
"backbone.layers.32.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
273 |
+
"backbone.layers.32.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
274 |
+
"backbone.layers.32.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
275 |
+
"backbone.layers.32.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
276 |
+
"backbone.layers.32.norm.weight": "model-00002-of-00003.safetensors",
|
277 |
+
"backbone.layers.33.mixer.A_log": "model-00002-of-00003.safetensors",
|
278 |
+
"backbone.layers.33.mixer.D": "model-00002-of-00003.safetensors",
|
279 |
+
"backbone.layers.33.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
280 |
+
"backbone.layers.33.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
281 |
+
"backbone.layers.33.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
282 |
+
"backbone.layers.33.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
283 |
+
"backbone.layers.33.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
284 |
+
"backbone.layers.33.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
285 |
+
"backbone.layers.33.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
286 |
+
"backbone.layers.33.norm.weight": "model-00002-of-00003.safetensors",
|
287 |
+
"backbone.layers.34.mixer.A_log": "model-00002-of-00003.safetensors",
|
288 |
+
"backbone.layers.34.mixer.D": "model-00002-of-00003.safetensors",
|
289 |
+
"backbone.layers.34.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
290 |
+
"backbone.layers.34.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
291 |
+
"backbone.layers.34.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
292 |
+
"backbone.layers.34.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
293 |
+
"backbone.layers.34.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
294 |
+
"backbone.layers.34.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
295 |
+
"backbone.layers.34.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
296 |
+
"backbone.layers.34.norm.weight": "model-00002-of-00003.safetensors",
|
297 |
+
"backbone.layers.35.mixer.A_log": "model-00002-of-00003.safetensors",
|
298 |
+
"backbone.layers.35.mixer.D": "model-00002-of-00003.safetensors",
|
299 |
+
"backbone.layers.35.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
300 |
+
"backbone.layers.35.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
301 |
+
"backbone.layers.35.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
302 |
+
"backbone.layers.35.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
303 |
+
"backbone.layers.35.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
304 |
+
"backbone.layers.35.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
305 |
+
"backbone.layers.35.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
306 |
+
"backbone.layers.35.norm.weight": "model-00002-of-00003.safetensors",
|
307 |
+
"backbone.layers.36.mixer.A_log": "model-00002-of-00003.safetensors",
|
308 |
+
"backbone.layers.36.mixer.D": "model-00002-of-00003.safetensors",
|
309 |
+
"backbone.layers.36.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
310 |
+
"backbone.layers.36.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
311 |
+
"backbone.layers.36.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
312 |
+
"backbone.layers.36.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
313 |
+
"backbone.layers.36.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
314 |
+
"backbone.layers.36.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
315 |
+
"backbone.layers.36.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
316 |
+
"backbone.layers.36.norm.weight": "model-00002-of-00003.safetensors",
|
317 |
+
"backbone.layers.37.mixer.A_log": "model-00002-of-00003.safetensors",
|
318 |
+
"backbone.layers.37.mixer.D": "model-00002-of-00003.safetensors",
|
319 |
+
"backbone.layers.37.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
320 |
+
"backbone.layers.37.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
321 |
+
"backbone.layers.37.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
322 |
+
"backbone.layers.37.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
323 |
+
"backbone.layers.37.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
324 |
+
"backbone.layers.37.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
325 |
+
"backbone.layers.37.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
326 |
+
"backbone.layers.37.norm.weight": "model-00002-of-00003.safetensors",
|
327 |
+
"backbone.layers.38.mixer.A_log": "model-00002-of-00003.safetensors",
|
328 |
+
"backbone.layers.38.mixer.D": "model-00002-of-00003.safetensors",
|
329 |
+
"backbone.layers.38.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
330 |
+
"backbone.layers.38.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
331 |
+
"backbone.layers.38.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
332 |
+
"backbone.layers.38.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
333 |
+
"backbone.layers.38.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
334 |
+
"backbone.layers.38.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
335 |
+
"backbone.layers.38.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
336 |
+
"backbone.layers.38.norm.weight": "model-00002-of-00003.safetensors",
|
337 |
+
"backbone.layers.39.mixer.A_log": "model-00002-of-00003.safetensors",
|
338 |
+
"backbone.layers.39.mixer.D": "model-00002-of-00003.safetensors",
|
339 |
+
"backbone.layers.39.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
340 |
+
"backbone.layers.39.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
341 |
+
"backbone.layers.39.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
342 |
+
"backbone.layers.39.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
343 |
+
"backbone.layers.39.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
344 |
+
"backbone.layers.39.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
345 |
+
"backbone.layers.39.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
346 |
+
"backbone.layers.39.norm.weight": "model-00002-of-00003.safetensors",
|
347 |
+
"backbone.layers.4.mixer.A_log": "model-00001-of-00003.safetensors",
|
348 |
+
"backbone.layers.4.mixer.D": "model-00001-of-00003.safetensors",
|
349 |
+
"backbone.layers.4.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
350 |
+
"backbone.layers.4.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
351 |
+
"backbone.layers.4.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
352 |
+
"backbone.layers.4.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
353 |
+
"backbone.layers.4.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
354 |
+
"backbone.layers.4.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
355 |
+
"backbone.layers.4.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
356 |
+
"backbone.layers.4.norm.weight": "model-00001-of-00003.safetensors",
|
357 |
+
"backbone.layers.40.mixer.A_log": "model-00002-of-00003.safetensors",
|
358 |
+
"backbone.layers.40.mixer.D": "model-00002-of-00003.safetensors",
|
359 |
+
"backbone.layers.40.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
360 |
+
"backbone.layers.40.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
361 |
+
"backbone.layers.40.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
362 |
+
"backbone.layers.40.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
363 |
+
"backbone.layers.40.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
364 |
+
"backbone.layers.40.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
365 |
+
"backbone.layers.40.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
366 |
+
"backbone.layers.40.norm.weight": "model-00002-of-00003.safetensors",
|
367 |
+
"backbone.layers.41.mixer.A_log": "model-00002-of-00003.safetensors",
|
368 |
+
"backbone.layers.41.mixer.D": "model-00002-of-00003.safetensors",
|
369 |
+
"backbone.layers.41.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
370 |
+
"backbone.layers.41.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
371 |
+
"backbone.layers.41.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
372 |
+
"backbone.layers.41.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
373 |
+
"backbone.layers.41.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
374 |
+
"backbone.layers.41.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
375 |
+
"backbone.layers.41.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
376 |
+
"backbone.layers.41.norm.weight": "model-00002-of-00003.safetensors",
|
377 |
+
"backbone.layers.42.mixer.A_log": "model-00002-of-00003.safetensors",
|
378 |
+
"backbone.layers.42.mixer.D": "model-00002-of-00003.safetensors",
|
379 |
+
"backbone.layers.42.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
380 |
+
"backbone.layers.42.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
381 |
+
"backbone.layers.42.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
382 |
+
"backbone.layers.42.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
383 |
+
"backbone.layers.42.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
384 |
+
"backbone.layers.42.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
385 |
+
"backbone.layers.42.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
386 |
+
"backbone.layers.42.norm.weight": "model-00002-of-00003.safetensors",
|
387 |
+
"backbone.layers.43.mixer.A_log": "model-00002-of-00003.safetensors",
|
388 |
+
"backbone.layers.43.mixer.D": "model-00002-of-00003.safetensors",
|
389 |
+
"backbone.layers.43.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
390 |
+
"backbone.layers.43.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
391 |
+
"backbone.layers.43.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
392 |
+
"backbone.layers.43.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
393 |
+
"backbone.layers.43.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
394 |
+
"backbone.layers.43.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
395 |
+
"backbone.layers.43.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
396 |
+
"backbone.layers.43.norm.weight": "model-00002-of-00003.safetensors",
|
397 |
+
"backbone.layers.44.mixer.A_log": "model-00002-of-00003.safetensors",
|
398 |
+
"backbone.layers.44.mixer.D": "model-00002-of-00003.safetensors",
|
399 |
+
"backbone.layers.44.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
400 |
+
"backbone.layers.44.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
401 |
+
"backbone.layers.44.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
402 |
+
"backbone.layers.44.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
403 |
+
"backbone.layers.44.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
404 |
+
"backbone.layers.44.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
405 |
+
"backbone.layers.44.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
406 |
+
"backbone.layers.44.norm.weight": "model-00002-of-00003.safetensors",
|
407 |
+
"backbone.layers.45.mixer.A_log": "model-00003-of-00003.safetensors",
|
408 |
+
"backbone.layers.45.mixer.D": "model-00003-of-00003.safetensors",
|
409 |
+
"backbone.layers.45.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
410 |
+
"backbone.layers.45.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
411 |
+
"backbone.layers.45.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
412 |
+
"backbone.layers.45.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
413 |
+
"backbone.layers.45.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
414 |
+
"backbone.layers.45.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
415 |
+
"backbone.layers.45.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
416 |
+
"backbone.layers.45.norm.weight": "model-00003-of-00003.safetensors",
|
417 |
+
"backbone.layers.46.mixer.A_log": "model-00003-of-00003.safetensors",
|
418 |
+
"backbone.layers.46.mixer.D": "model-00003-of-00003.safetensors",
|
419 |
+
"backbone.layers.46.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
420 |
+
"backbone.layers.46.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
421 |
+
"backbone.layers.46.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
422 |
+
"backbone.layers.46.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
423 |
+
"backbone.layers.46.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
424 |
+
"backbone.layers.46.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
425 |
+
"backbone.layers.46.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
426 |
+
"backbone.layers.46.norm.weight": "model-00003-of-00003.safetensors",
|
427 |
+
"backbone.layers.47.mixer.A_log": "model-00003-of-00003.safetensors",
|
428 |
+
"backbone.layers.47.mixer.D": "model-00003-of-00003.safetensors",
|
429 |
+
"backbone.layers.47.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
430 |
+
"backbone.layers.47.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
431 |
+
"backbone.layers.47.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
432 |
+
"backbone.layers.47.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
433 |
+
"backbone.layers.47.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
434 |
+
"backbone.layers.47.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
435 |
+
"backbone.layers.47.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
436 |
+
"backbone.layers.47.norm.weight": "model-00003-of-00003.safetensors",
|
437 |
+
"backbone.layers.48.mixer.A_log": "model-00003-of-00003.safetensors",
|
438 |
+
"backbone.layers.48.mixer.D": "model-00003-of-00003.safetensors",
|
439 |
+
"backbone.layers.48.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
440 |
+
"backbone.layers.48.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
441 |
+
"backbone.layers.48.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
442 |
+
"backbone.layers.48.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
443 |
+
"backbone.layers.48.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
444 |
+
"backbone.layers.48.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
445 |
+
"backbone.layers.48.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
446 |
+
"backbone.layers.48.norm.weight": "model-00003-of-00003.safetensors",
|
447 |
+
"backbone.layers.49.mixer.A_log": "model-00003-of-00003.safetensors",
|
448 |
+
"backbone.layers.49.mixer.D": "model-00003-of-00003.safetensors",
|
449 |
+
"backbone.layers.49.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
450 |
+
"backbone.layers.49.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
451 |
+
"backbone.layers.49.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
452 |
+
"backbone.layers.49.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
453 |
+
"backbone.layers.49.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
454 |
+
"backbone.layers.49.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
455 |
+
"backbone.layers.49.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
456 |
+
"backbone.layers.49.norm.weight": "model-00003-of-00003.safetensors",
|
457 |
+
"backbone.layers.5.mixer.A_log": "model-00001-of-00003.safetensors",
|
458 |
+
"backbone.layers.5.mixer.D": "model-00001-of-00003.safetensors",
|
459 |
+
"backbone.layers.5.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
460 |
+
"backbone.layers.5.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
461 |
+
"backbone.layers.5.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
462 |
+
"backbone.layers.5.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
463 |
+
"backbone.layers.5.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
464 |
+
"backbone.layers.5.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
465 |
+
"backbone.layers.5.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
466 |
+
"backbone.layers.5.norm.weight": "model-00001-of-00003.safetensors",
|
467 |
+
"backbone.layers.50.mixer.A_log": "model-00003-of-00003.safetensors",
|
468 |
+
"backbone.layers.50.mixer.D": "model-00003-of-00003.safetensors",
|
469 |
+
"backbone.layers.50.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
470 |
+
"backbone.layers.50.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
471 |
+
"backbone.layers.50.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
472 |
+
"backbone.layers.50.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
473 |
+
"backbone.layers.50.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
474 |
+
"backbone.layers.50.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
475 |
+
"backbone.layers.50.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
476 |
+
"backbone.layers.50.norm.weight": "model-00003-of-00003.safetensors",
|
477 |
+
"backbone.layers.51.mixer.A_log": "model-00003-of-00003.safetensors",
|
478 |
+
"backbone.layers.51.mixer.D": "model-00003-of-00003.safetensors",
|
479 |
+
"backbone.layers.51.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
480 |
+
"backbone.layers.51.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
481 |
+
"backbone.layers.51.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
482 |
+
"backbone.layers.51.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
483 |
+
"backbone.layers.51.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
484 |
+
"backbone.layers.51.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
485 |
+
"backbone.layers.51.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
486 |
+
"backbone.layers.51.norm.weight": "model-00003-of-00003.safetensors",
|
487 |
+
"backbone.layers.52.mixer.A_log": "model-00003-of-00003.safetensors",
|
488 |
+
"backbone.layers.52.mixer.D": "model-00003-of-00003.safetensors",
|
489 |
+
"backbone.layers.52.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
490 |
+
"backbone.layers.52.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
491 |
+
"backbone.layers.52.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
492 |
+
"backbone.layers.52.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
493 |
+
"backbone.layers.52.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
494 |
+
"backbone.layers.52.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
495 |
+
"backbone.layers.52.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
496 |
+
"backbone.layers.52.norm.weight": "model-00003-of-00003.safetensors",
|
497 |
+
"backbone.layers.53.mixer.A_log": "model-00003-of-00003.safetensors",
|
498 |
+
"backbone.layers.53.mixer.D": "model-00003-of-00003.safetensors",
|
499 |
+
"backbone.layers.53.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
500 |
+
"backbone.layers.53.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
501 |
+
"backbone.layers.53.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
502 |
+
"backbone.layers.53.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
503 |
+
"backbone.layers.53.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
504 |
+
"backbone.layers.53.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
505 |
+
"backbone.layers.53.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
506 |
+
"backbone.layers.53.norm.weight": "model-00003-of-00003.safetensors",
|
507 |
+
"backbone.layers.54.mixer.A_log": "model-00003-of-00003.safetensors",
|
508 |
+
"backbone.layers.54.mixer.D": "model-00003-of-00003.safetensors",
|
509 |
+
"backbone.layers.54.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
510 |
+
"backbone.layers.54.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
511 |
+
"backbone.layers.54.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
512 |
+
"backbone.layers.54.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
513 |
+
"backbone.layers.54.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
514 |
+
"backbone.layers.54.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
515 |
+
"backbone.layers.54.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
516 |
+
"backbone.layers.54.norm.weight": "model-00003-of-00003.safetensors",
|
517 |
+
"backbone.layers.55.mixer.A_log": "model-00003-of-00003.safetensors",
|
518 |
+
"backbone.layers.55.mixer.D": "model-00003-of-00003.safetensors",
|
519 |
+
"backbone.layers.55.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
520 |
+
"backbone.layers.55.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
521 |
+
"backbone.layers.55.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
522 |
+
"backbone.layers.55.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
523 |
+
"backbone.layers.55.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
524 |
+
"backbone.layers.55.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
525 |
+
"backbone.layers.55.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
526 |
+
"backbone.layers.55.norm.weight": "model-00003-of-00003.safetensors",
|
527 |
+
"backbone.layers.56.mixer.A_log": "model-00003-of-00003.safetensors",
|
528 |
+
"backbone.layers.56.mixer.D": "model-00003-of-00003.safetensors",
|
529 |
+
"backbone.layers.56.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
530 |
+
"backbone.layers.56.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
531 |
+
"backbone.layers.56.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
532 |
+
"backbone.layers.56.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
533 |
+
"backbone.layers.56.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
534 |
+
"backbone.layers.56.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
535 |
+
"backbone.layers.56.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
536 |
+
"backbone.layers.56.norm.weight": "model-00003-of-00003.safetensors",
|
537 |
+
"backbone.layers.57.mixer.A_log": "model-00003-of-00003.safetensors",
|
538 |
+
"backbone.layers.57.mixer.D": "model-00003-of-00003.safetensors",
|
539 |
+
"backbone.layers.57.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
540 |
+
"backbone.layers.57.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
541 |
+
"backbone.layers.57.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
542 |
+
"backbone.layers.57.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
543 |
+
"backbone.layers.57.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
544 |
+
"backbone.layers.57.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
545 |
+
"backbone.layers.57.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
546 |
+
"backbone.layers.57.norm.weight": "model-00003-of-00003.safetensors",
|
547 |
+
"backbone.layers.58.mixer.A_log": "model-00003-of-00003.safetensors",
|
548 |
+
"backbone.layers.58.mixer.D": "model-00003-of-00003.safetensors",
|
549 |
+
"backbone.layers.58.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
550 |
+
"backbone.layers.58.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
551 |
+
"backbone.layers.58.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
552 |
+
"backbone.layers.58.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
553 |
+
"backbone.layers.58.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
554 |
+
"backbone.layers.58.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
555 |
+
"backbone.layers.58.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
556 |
+
"backbone.layers.58.norm.weight": "model-00003-of-00003.safetensors",
|
557 |
+
"backbone.layers.59.mixer.A_log": "model-00003-of-00003.safetensors",
|
558 |
+
"backbone.layers.59.mixer.D": "model-00003-of-00003.safetensors",
|
559 |
+
"backbone.layers.59.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
560 |
+
"backbone.layers.59.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
561 |
+
"backbone.layers.59.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
562 |
+
"backbone.layers.59.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
563 |
+
"backbone.layers.59.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
564 |
+
"backbone.layers.59.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
565 |
+
"backbone.layers.59.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
566 |
+
"backbone.layers.59.norm.weight": "model-00003-of-00003.safetensors",
|
567 |
+
"backbone.layers.6.mixer.A_log": "model-00001-of-00003.safetensors",
|
568 |
+
"backbone.layers.6.mixer.D": "model-00001-of-00003.safetensors",
|
569 |
+
"backbone.layers.6.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
570 |
+
"backbone.layers.6.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
571 |
+
"backbone.layers.6.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
572 |
+
"backbone.layers.6.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
573 |
+
"backbone.layers.6.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
574 |
+
"backbone.layers.6.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
575 |
+
"backbone.layers.6.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
576 |
+
"backbone.layers.6.norm.weight": "model-00001-of-00003.safetensors",
|
577 |
+
"backbone.layers.60.mixer.A_log": "model-00003-of-00003.safetensors",
|
578 |
+
"backbone.layers.60.mixer.D": "model-00003-of-00003.safetensors",
|
579 |
+
"backbone.layers.60.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
580 |
+
"backbone.layers.60.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
581 |
+
"backbone.layers.60.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
582 |
+
"backbone.layers.60.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
583 |
+
"backbone.layers.60.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
584 |
+
"backbone.layers.60.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
585 |
+
"backbone.layers.60.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
586 |
+
"backbone.layers.60.norm.weight": "model-00003-of-00003.safetensors",
|
587 |
+
"backbone.layers.61.mixer.A_log": "model-00003-of-00003.safetensors",
|
588 |
+
"backbone.layers.61.mixer.D": "model-00003-of-00003.safetensors",
|
589 |
+
"backbone.layers.61.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
590 |
+
"backbone.layers.61.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
591 |
+
"backbone.layers.61.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
592 |
+
"backbone.layers.61.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
593 |
+
"backbone.layers.61.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
594 |
+
"backbone.layers.61.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
595 |
+
"backbone.layers.61.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
596 |
+
"backbone.layers.61.norm.weight": "model-00003-of-00003.safetensors",
|
597 |
+
"backbone.layers.62.mixer.A_log": "model-00003-of-00003.safetensors",
|
598 |
+
"backbone.layers.62.mixer.D": "model-00003-of-00003.safetensors",
|
599 |
+
"backbone.layers.62.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
600 |
+
"backbone.layers.62.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
601 |
+
"backbone.layers.62.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
602 |
+
"backbone.layers.62.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
603 |
+
"backbone.layers.62.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
604 |
+
"backbone.layers.62.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
605 |
+
"backbone.layers.62.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
606 |
+
"backbone.layers.62.norm.weight": "model-00003-of-00003.safetensors",
|
607 |
+
"backbone.layers.63.mixer.A_log": "model-00003-of-00003.safetensors",
|
608 |
+
"backbone.layers.63.mixer.D": "model-00003-of-00003.safetensors",
|
609 |
+
"backbone.layers.63.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
610 |
+
"backbone.layers.63.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
611 |
+
"backbone.layers.63.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
612 |
+
"backbone.layers.63.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
613 |
+
"backbone.layers.63.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
614 |
+
"backbone.layers.63.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
615 |
+
"backbone.layers.63.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
616 |
+
"backbone.layers.63.norm.weight": "model-00003-of-00003.safetensors",
|
617 |
+
"backbone.layers.7.mixer.A_log": "model-00001-of-00003.safetensors",
|
618 |
+
"backbone.layers.7.mixer.D": "model-00001-of-00003.safetensors",
|
619 |
+
"backbone.layers.7.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
620 |
+
"backbone.layers.7.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
621 |
+
"backbone.layers.7.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
622 |
+
"backbone.layers.7.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
623 |
+
"backbone.layers.7.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
624 |
+
"backbone.layers.7.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
625 |
+
"backbone.layers.7.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
626 |
+
"backbone.layers.7.norm.weight": "model-00001-of-00003.safetensors",
|
627 |
+
"backbone.layers.8.mixer.A_log": "model-00001-of-00003.safetensors",
|
628 |
+
"backbone.layers.8.mixer.D": "model-00001-of-00003.safetensors",
|
629 |
+
"backbone.layers.8.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
630 |
+
"backbone.layers.8.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
631 |
+
"backbone.layers.8.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
632 |
+
"backbone.layers.8.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
633 |
+
"backbone.layers.8.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
634 |
+
"backbone.layers.8.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
635 |
+
"backbone.layers.8.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
636 |
+
"backbone.layers.8.norm.weight": "model-00001-of-00003.safetensors",
|
637 |
+
"backbone.layers.9.mixer.A_log": "model-00001-of-00003.safetensors",
|
638 |
+
"backbone.layers.9.mixer.D": "model-00001-of-00003.safetensors",
|
639 |
+
"backbone.layers.9.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
640 |
+
"backbone.layers.9.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
641 |
+
"backbone.layers.9.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
642 |
+
"backbone.layers.9.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
643 |
+
"backbone.layers.9.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
644 |
+
"backbone.layers.9.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
645 |
+
"backbone.layers.9.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
646 |
+
"backbone.layers.9.norm.weight": "model-00001-of-00003.safetensors",
|
647 |
+
"backbone.norm_f.weight": "model-00003-of-00003.safetensors",
|
648 |
+
"lm_head.weight": "model-00003-of-00003.safetensors"
|
649 |
+
}
|
650 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
">>TITLE<<",
|
4 |
+
">>ABSTRACT<<",
|
5 |
+
">>INTRODUCTION<<",
|
6 |
+
">>SUMMARY<<",
|
7 |
+
">>COMMENT<<",
|
8 |
+
">>ANSWER<<",
|
9 |
+
">>QUESTION<<",
|
10 |
+
"assistant",
|
11 |
+
"<|begin_of_text|>",
|
12 |
+
"<|im_start|>",
|
13 |
+
"<|im_end|>"
|
14 |
+
],
|
15 |
+
"bos_token": {
|
16 |
+
"content": "<|begin_of_text|>",
|
17 |
+
"lstrip": false,
|
18 |
+
"normalized": false,
|
19 |
+
"rstrip": false,
|
20 |
+
"single_word": false
|
21 |
+
},
|
22 |
+
"eos_token": {
|
23 |
+
"content": "<|end_of_text|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false
|
28 |
+
},
|
29 |
+
"pad_token": "<|end_of_text|>"
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": ">>TITLE<<",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": ">>ABSTRACT<<",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": ">>INTRODUCTION<<",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": ">>SUMMARY<<",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"4": {
|
37 |
+
"content": ">>COMMENT<<",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"5": {
|
45 |
+
"content": ">>ANSWER<<",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"6": {
|
53 |
+
"content": ">>QUESTION<<",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"7": {
|
61 |
+
"content": "assistant",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"8": {
|
69 |
+
"content": "<|begin_of_text|>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"9": {
|
77 |
+
"content": "<|im_start|>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"10": {
|
85 |
+
"content": "<|im_end|>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"11": {
|
93 |
+
"content": "<|end_of_text|>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
}
|
100 |
+
},
|
101 |
+
"additional_special_tokens": [
|
102 |
+
">>TITLE<<",
|
103 |
+
">>ABSTRACT<<",
|
104 |
+
">>INTRODUCTION<<",
|
105 |
+
">>SUMMARY<<",
|
106 |
+
">>COMMENT<<",
|
107 |
+
">>ANSWER<<",
|
108 |
+
">>QUESTION<<",
|
109 |
+
"assistant",
|
110 |
+
"<|begin_of_text|>",
|
111 |
+
"<|im_start|>",
|
112 |
+
"<|im_end|>"
|
113 |
+
],
|
114 |
+
"bos_token": "<|begin_of_text|>",
|
115 |
+
"chat_template": "{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
116 |
+
"clean_up_tokenization_spaces": true,
|
117 |
+
"eos_token": "<|end_of_text|>",
|
118 |
+
"extra_special_tokens": {},
|
119 |
+
"max_length": null,
|
120 |
+
"model_input_names": [
|
121 |
+
"input_ids",
|
122 |
+
"attention_mask"
|
123 |
+
],
|
124 |
+
"model_max_length": 1000000000000000019884624838656,
|
125 |
+
"pad_to_multiple_of": null,
|
126 |
+
"pad_token": "<|end_of_text|>",
|
127 |
+
"pad_token_type_id": 0,
|
128 |
+
"padding_side": "left",
|
129 |
+
"tokenizer_class": "PreTrainedTokenizer"
|
130 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"total_flos": 3.616227566899167e+18,
|
3 |
+
"train_loss": 16.595592213948567,
|
4 |
+
"train_runtime": 29081.677,
|
5 |
+
"train_samples": 16610,
|
6 |
+
"train_samples_per_second": 0.827,
|
7 |
+
"train_steps_per_second": 0.013
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,706 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": null,
|
3 |
+
"best_metric": null,
|
4 |
+
"best_model_checkpoint": null,
|
5 |
+
"epoch": 0.998003992015968,
|
6 |
+
"eval_steps": 50,
|
7 |
+
"global_step": 375,
|
8 |
+
"is_hyper_param_search": false,
|
9 |
+
"is_local_process_zero": true,
|
10 |
+
"is_world_process_zero": true,
|
11 |
+
"log_history": [
|
12 |
+
{
|
13 |
+
"epoch": 0.01330671989354624,
|
14 |
+
"grad_norm": 38.0893895691,
|
15 |
+
"learning_rate": 2.631578947368421e-06,
|
16 |
+
"loss": 9.4719,
|
17 |
+
"mean_token_accuracy": 0.6992475613951683,
|
18 |
+
"step": 5
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 0.02661343978709248,
|
22 |
+
"grad_norm": 53.38062892110183,
|
23 |
+
"learning_rate": 5.263157894736842e-06,
|
24 |
+
"loss": 9.2617,
|
25 |
+
"mean_token_accuracy": 0.7013110458850861,
|
26 |
+
"step": 10
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.03992015968063872,
|
30 |
+
"grad_norm": 65.59379133263475,
|
31 |
+
"learning_rate": 7.894736842105265e-06,
|
32 |
+
"loss": 8.8052,
|
33 |
+
"mean_token_accuracy": 0.7065529704093934,
|
34 |
+
"step": 15
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 0.05322687957418496,
|
38 |
+
"grad_norm": 30.823233386013126,
|
39 |
+
"learning_rate": 1.0526315789473684e-05,
|
40 |
+
"loss": 8.1585,
|
41 |
+
"mean_token_accuracy": 0.719629879295826,
|
42 |
+
"step": 20
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 0.0665335994677312,
|
46 |
+
"grad_norm": 12.66541979902211,
|
47 |
+
"learning_rate": 1.3157894736842108e-05,
|
48 |
+
"loss": 7.3748,
|
49 |
+
"mean_token_accuracy": 0.740014499425888,
|
50 |
+
"step": 25
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.07984031936127745,
|
54 |
+
"grad_norm": 10.709230045785015,
|
55 |
+
"learning_rate": 1.578947368421053e-05,
|
56 |
+
"loss": 7.1481,
|
57 |
+
"mean_token_accuracy": 0.7436378166079521,
|
58 |
+
"step": 30
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.09314703925482369,
|
62 |
+
"grad_norm": 7.432960167563066,
|
63 |
+
"learning_rate": 1.8421052631578947e-05,
|
64 |
+
"loss": 6.9424,
|
65 |
+
"mean_token_accuracy": 0.7486263796687126,
|
66 |
+
"step": 35
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.10645375914836992,
|
70 |
+
"grad_norm": 10.045989605681791,
|
71 |
+
"learning_rate": 1.9998261969639324e-05,
|
72 |
+
"loss": 6.9028,
|
73 |
+
"mean_token_accuracy": 0.7475503668189049,
|
74 |
+
"step": 40
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.11976047904191617,
|
78 |
+
"grad_norm": 15.965640756107303,
|
79 |
+
"learning_rate": 1.9978716065702566e-05,
|
80 |
+
"loss": 7.2718,
|
81 |
+
"mean_token_accuracy": 0.7349641278386116,
|
82 |
+
"step": 45
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.1330671989354624,
|
86 |
+
"grad_norm": 27.77458817629002,
|
87 |
+
"learning_rate": 1.9937494319239112e-05,
|
88 |
+
"loss": 7.3623,
|
89 |
+
"mean_token_accuracy": 0.7310615047812462,
|
90 |
+
"step": 50
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.1330671989354624,
|
94 |
+
"eval_loss": 1.008537769317627,
|
95 |
+
"eval_mean_token_accuracy": 0.7182760106192695,
|
96 |
+
"eval_runtime": 42.3882,
|
97 |
+
"eval_samples_per_second": 3.397,
|
98 |
+
"eval_steps_per_second": 0.425,
|
99 |
+
"step": 50
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.14637391882900866,
|
103 |
+
"grad_norm": 30.81470758273484,
|
104 |
+
"learning_rate": 1.9874686272438467e-05,
|
105 |
+
"loss": 7.2943,
|
106 |
+
"mean_token_accuracy": 0.7337011635303498,
|
107 |
+
"step": 55
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.1596806387225549,
|
111 |
+
"grad_norm": 22.17371294352614,
|
112 |
+
"learning_rate": 1.979042835741503e-05,
|
113 |
+
"loss": 7.104,
|
114 |
+
"mean_token_accuracy": 0.7383959114551544,
|
115 |
+
"step": 60
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.17298735861610112,
|
119 |
+
"grad_norm": 27.90713548690936,
|
120 |
+
"learning_rate": 1.968490359984923e-05,
|
121 |
+
"loss": 7.1833,
|
122 |
+
"mean_token_accuracy": 0.7363018915057182,
|
123 |
+
"step": 65
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.18629407850964738,
|
127 |
+
"grad_norm": 9.001486401205879,
|
128 |
+
"learning_rate": 1.9558341221417744e-05,
|
129 |
+
"loss": 7.05,
|
130 |
+
"mean_token_accuracy": 0.740586844086647,
|
131 |
+
"step": 70
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 0.1996007984031936,
|
135 |
+
"grad_norm": 13.898951307519155,
|
136 |
+
"learning_rate": 1.9411016141876438e-05,
|
137 |
+
"loss": 7.0786,
|
138 |
+
"mean_token_accuracy": 0.7393299728631973,
|
139 |
+
"step": 75
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"epoch": 0.21290751829673984,
|
143 |
+
"grad_norm": 44.17413162889863,
|
144 |
+
"learning_rate": 1.9243248381877605e-05,
|
145 |
+
"loss": 7.513,
|
146 |
+
"mean_token_accuracy": 0.7232646465301513,
|
147 |
+
"step": 80
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.2262142381902861,
|
151 |
+
"grad_norm": 43.276281867208816,
|
152 |
+
"learning_rate": 1.9055402367818673e-05,
|
153 |
+
"loss": 7.2214,
|
154 |
+
"mean_token_accuracy": 0.7344184964895248,
|
155 |
+
"step": 85
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 0.23952095808383234,
|
159 |
+
"grad_norm": 22.007621479836395,
|
160 |
+
"learning_rate": 1.8847886140232438e-05,
|
161 |
+
"loss": 7.1625,
|
162 |
+
"mean_token_accuracy": 0.735144229233265,
|
163 |
+
"step": 90
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.2528276779773786,
|
167 |
+
"grad_norm": 77.4740488466291,
|
168 |
+
"learning_rate": 1.862115046743831e-05,
|
169 |
+
"loss": 7.5932,
|
170 |
+
"mean_token_accuracy": 0.722845695912838,
|
171 |
+
"step": 95
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.2661343978709248,
|
175 |
+
"grad_norm": 1066.7215003063964,
|
176 |
+
"learning_rate": 1.8375687866379988e-05,
|
177 |
+
"loss": 7.4423,
|
178 |
+
"mean_token_accuracy": 0.7269001781940461,
|
179 |
+
"step": 100
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.2661343978709248,
|
183 |
+
"eval_loss": 1.0586838722229004,
|
184 |
+
"eval_mean_token_accuracy": 0.6958943770991431,
|
185 |
+
"eval_runtime": 42.4569,
|
186 |
+
"eval_samples_per_second": 3.392,
|
187 |
+
"eval_steps_per_second": 0.424,
|
188 |
+
"step": 100
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.27944111776447106,
|
192 |
+
"grad_norm": 923.4336165050305,
|
193 |
+
"learning_rate": 1.811203153277641e-05,
|
194 |
+
"loss": 8.4501,
|
195 |
+
"mean_token_accuracy": 0.6929014056921006,
|
196 |
+
"step": 105
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 0.2927478376580173,
|
200 |
+
"grad_norm": 10253.700005495137,
|
201 |
+
"learning_rate": 1.7830754182909985e-05,
|
202 |
+
"loss": 11.581,
|
203 |
+
"mean_token_accuracy": 0.6142643451690674,
|
204 |
+
"step": 110
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.3060545575515635,
|
208 |
+
"grad_norm": 11508.216656593022,
|
209 |
+
"learning_rate": 1.753246680956795e-05,
|
210 |
+
"loss": 15.7105,
|
211 |
+
"mean_token_accuracy": 0.5149824447929859,
|
212 |
+
"step": 115
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.3193612774451098,
|
216 |
+
"grad_norm": 6036.292381336853,
|
217 |
+
"learning_rate": 1.721781735483921e-05,
|
218 |
+
"loss": 26.2876,
|
219 |
+
"mean_token_accuracy": 0.33059981614351275,
|
220 |
+
"step": 120
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.33266799733865604,
|
224 |
+
"grad_norm": 26623.625140159445,
|
225 |
+
"learning_rate": 1.6887489302649657e-05,
|
226 |
+
"loss": 30.2414,
|
227 |
+
"mean_token_accuracy": 0.26836080476641655,
|
228 |
+
"step": 125
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 0.34597471723220224,
|
232 |
+
"grad_norm": 213666.71326672958,
|
233 |
+
"learning_rate": 1.654220019409317e-05,
|
234 |
+
"loss": 36.7917,
|
235 |
+
"mean_token_accuracy": 0.20126449912786484,
|
236 |
+
"step": 130
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.3592814371257485,
|
240 |
+
"grad_norm": 281204.55298403726,
|
241 |
+
"learning_rate": 1.6182700068783463e-05,
|
242 |
+
"loss": 53.894,
|
243 |
+
"mean_token_accuracy": 0.08266483591869474,
|
244 |
+
"step": 135
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 0.37258815701929476,
|
248 |
+
"grad_norm": 274791.48096197617,
|
249 |
+
"learning_rate": 1.580976983561235e-05,
|
250 |
+
"loss": 58.3125,
|
251 |
+
"mean_token_accuracy": 0.06163843311369419,
|
252 |
+
"step": 140
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 0.38589487691284097,
|
256 |
+
"grad_norm": 9564.75792140504,
|
257 |
+
"learning_rate": 1.5424219576453526e-05,
|
258 |
+
"loss": 45.3478,
|
259 |
+
"mean_token_accuracy": 0.12734813932329417,
|
260 |
+
"step": 145
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.3992015968063872,
|
264 |
+
"grad_norm": 6120.107227530501,
|
265 |
+
"learning_rate": 1.5026886786496624e-05,
|
266 |
+
"loss": 42.2261,
|
267 |
+
"mean_token_accuracy": 0.1591544572263956,
|
268 |
+
"step": 150
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.3992015968063872,
|
272 |
+
"eval_loss": 4.92734432220459,
|
273 |
+
"eval_mean_token_accuracy": 0.1774691359864341,
|
274 |
+
"eval_runtime": 42.2395,
|
275 |
+
"eval_samples_per_second": 3.409,
|
276 |
+
"eval_steps_per_second": 0.426,
|
277 |
+
"step": 150
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 0.4125083166999335,
|
281 |
+
"grad_norm": 13441.595281708549,
|
282 |
+
"learning_rate": 1.46186345550338e-05,
|
283 |
+
"loss": 32.8561,
|
284 |
+
"mean_token_accuracy": 0.23304792679846287,
|
285 |
+
"step": 155
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.4258150365934797,
|
289 |
+
"grad_norm": 4366.951799070855,
|
290 |
+
"learning_rate": 1.4200349690650654e-05,
|
291 |
+
"loss": 26.1181,
|
292 |
+
"mean_token_accuracy": 0.3177220694720745,
|
293 |
+
"step": 160
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 0.43912175648702595,
|
297 |
+
"grad_norm": 8486.995137743008,
|
298 |
+
"learning_rate": 1.3772940794893916e-05,
|
299 |
+
"loss": 28.5985,
|
300 |
+
"mean_token_accuracy": 0.28858516551554203,
|
301 |
+
"step": 165
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 0.4524284763805722,
|
305 |
+
"grad_norm": 4760.402708498517,
|
306 |
+
"learning_rate": 1.3337336288600297e-05,
|
307 |
+
"loss": 24.7618,
|
308 |
+
"mean_token_accuracy": 0.3370695985853672,
|
309 |
+
"step": 170
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.4657351962741184,
|
313 |
+
"grad_norm": 1237.143262994326,
|
314 |
+
"learning_rate": 1.2894482395173695e-05,
|
315 |
+
"loss": 17.015,
|
316 |
+
"mean_token_accuracy": 0.4780235022306442,
|
317 |
+
"step": 175
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.47904191616766467,
|
321 |
+
"grad_norm": 408.8332305447992,
|
322 |
+
"learning_rate": 1.24453410851916e-05,
|
323 |
+
"loss": 15.019,
|
324 |
+
"mean_token_accuracy": 0.516390411555767,
|
325 |
+
"step": 180
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.49234863606121093,
|
329 |
+
"grad_norm": 311.65890181237427,
|
330 |
+
"learning_rate": 1.1990887986805295e-05,
|
331 |
+
"loss": 13.0538,
|
332 |
+
"mean_token_accuracy": 0.5649969473481178,
|
333 |
+
"step": 185
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.5056553559547572,
|
337 |
+
"grad_norm": 218.78464454962847,
|
338 |
+
"learning_rate": 1.1532110266473026e-05,
|
339 |
+
"loss": 11.4017,
|
340 |
+
"mean_token_accuracy": 0.6076564386487007,
|
341 |
+
"step": 190
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 0.5189620758483033,
|
345 |
+
"grad_norm": 248.3901525774538,
|
346 |
+
"learning_rate": 1.1070004484629543e-05,
|
347 |
+
"loss": 10.3675,
|
348 |
+
"mean_token_accuracy": 0.6390743300318718,
|
349 |
+
"step": 195
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 0.5322687957418496,
|
353 |
+
"grad_norm": 68.79121302231147,
|
354 |
+
"learning_rate": 1.0605574430949983e-05,
|
355 |
+
"loss": 9.2733,
|
356 |
+
"mean_token_accuracy": 0.6695673123002053,
|
357 |
+
"step": 200
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.5322687957418496,
|
361 |
+
"eval_loss": 1.2745658159255981,
|
362 |
+
"eval_mean_token_accuracy": 0.6473477118545108,
|
363 |
+
"eval_runtime": 42.3799,
|
364 |
+
"eval_samples_per_second": 3.398,
|
365 |
+
"eval_steps_per_second": 0.425,
|
366 |
+
"step": 200
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.5455755156353959,
|
370 |
+
"grad_norm": 61.494613995295225,
|
371 |
+
"learning_rate": 1.0139828943910358e-05,
|
372 |
+
"loss": 8.6282,
|
373 |
+
"mean_token_accuracy": 0.6900610521435737,
|
374 |
+
"step": 205
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.5588822355289421,
|
378 |
+
"grad_norm": 223.47361816320114,
|
379 |
+
"learning_rate": 9.673779719380967e-06,
|
380 |
+
"loss": 8.8734,
|
381 |
+
"mean_token_accuracy": 0.6839690148830414,
|
382 |
+
"step": 210
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.5721889554224884,
|
386 |
+
"grad_norm": 311.485197048925,
|
387 |
+
"learning_rate": 9.208439113012984e-06,
|
388 |
+
"loss": 9.6346,
|
389 |
+
"mean_token_accuracy": 0.6596978038549424,
|
390 |
+
"step": 215
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 0.5854956753160346,
|
394 |
+
"grad_norm": 208.95277149419533,
|
395 |
+
"learning_rate": 8.744817941191862e-06,
|
396 |
+
"loss": 9.8742,
|
397 |
+
"mean_token_accuracy": 0.6521520212292671,
|
398 |
+
"step": 220
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 0.5988023952095808,
|
402 |
+
"grad_norm": 99.55141840914388,
|
403 |
+
"learning_rate": 8.283923285334304e-06,
|
404 |
+
"loss": 10.0645,
|
405 |
+
"mean_token_accuracy": 0.6457211509346962,
|
406 |
+
"step": 225
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 0.612109115103127,
|
410 |
+
"grad_norm": 113.01850407325877,
|
411 |
+
"learning_rate": 7.826756304298428e-06,
|
412 |
+
"loss": 9.6991,
|
413 |
+
"mean_token_accuracy": 0.6567307710647583,
|
414 |
+
"step": 230
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.6254158349966733,
|
418 |
+
"grad_norm": 122.00372512450222,
|
419 |
+
"learning_rate": 7.3743100596589e-06,
|
420 |
+
"loss": 9.3977,
|
421 |
+
"mean_token_accuracy": 0.6660859316587449,
|
422 |
+
"step": 235
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.6387225548902196,
|
426 |
+
"grad_norm": 141.28653030104314,
|
427 |
+
"learning_rate": 6.92756735857107e-06,
|
428 |
+
"loss": 9.916,
|
429 |
+
"mean_token_accuracy": 0.6507371798157692,
|
430 |
+
"step": 240
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 0.6520292747837658,
|
434 |
+
"grad_norm": 807.7008160726642,
|
435 |
+
"learning_rate": 6.487498618909845e-06,
|
436 |
+
"loss": 9.8794,
|
437 |
+
"mean_token_accuracy": 0.6521420940756798,
|
438 |
+
"step": 245
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 0.6653359946773121,
|
442 |
+
"grad_norm": 12179.703084325536,
|
443 |
+
"learning_rate": 6.0550597613206205e-06,
|
444 |
+
"loss": 10.3914,
|
445 |
+
"mean_token_accuracy": 0.6389522299170494,
|
446 |
+
"step": 250
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.6653359946773121,
|
450 |
+
"eval_loss": 1.7774240970611572,
|
451 |
+
"eval_mean_token_accuracy": 0.5449769298235575,
|
452 |
+
"eval_runtime": 42.2375,
|
453 |
+
"eval_samples_per_second": 3.409,
|
454 |
+
"eval_steps_per_second": 0.426,
|
455 |
+
"step": 250
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 0.6786427145708582,
|
459 |
+
"grad_norm": 1054.76927310761,
|
460 |
+
"learning_rate": 5.631190132761247e-06,
|
461 |
+
"loss": 11.7133,
|
462 |
+
"mean_token_accuracy": 0.5997588485479355,
|
463 |
+
"step": 255
|
464 |
+
},
|
465 |
+
{
|
466 |
+
"epoch": 0.6919494344644045,
|
467 |
+
"grad_norm": 1424.9333125346188,
|
468 |
+
"learning_rate": 5.216810466045448e-06,
|
469 |
+
"loss": 12.5735,
|
470 |
+
"mean_token_accuracy": 0.5747481673955918,
|
471 |
+
"step": 260
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.7052561543579507,
|
475 |
+
"grad_norm": 798.7973283165478,
|
476 |
+
"learning_rate": 4.812820879820034e-06,
|
477 |
+
"loss": 13.4974,
|
478 |
+
"mean_token_accuracy": 0.5521100461483002,
|
479 |
+
"step": 265
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.718562874251497,
|
483 |
+
"grad_norm": 1790.9039210107235,
|
484 |
+
"learning_rate": 4.420098923320378e-06,
|
485 |
+
"loss": 14.4898,
|
486 |
+
"mean_token_accuracy": 0.5296176724135876,
|
487 |
+
"step": 270
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 0.7318695941450433,
|
491 |
+
"grad_norm": 829.5583452937811,
|
492 |
+
"learning_rate": 4.0394976701513235e-06,
|
493 |
+
"loss": 14.5873,
|
494 |
+
"mean_token_accuracy": 0.5268749997019768,
|
495 |
+
"step": 275
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.7451763140385895,
|
499 |
+
"grad_norm": 6150.368162782374,
|
500 |
+
"learning_rate": 3.671843865234238e-06,
|
501 |
+
"loss": 14.6091,
|
502 |
+
"mean_token_accuracy": 0.5281791850924492,
|
503 |
+
"step": 280
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"epoch": 0.7584830339321357,
|
507 |
+
"grad_norm": 29207.957135047905,
|
508 |
+
"learning_rate": 3.3179361289454694e-06,
|
509 |
+
"loss": 16.9682,
|
510 |
+
"mean_token_accuracy": 0.48243742287158964,
|
511 |
+
"step": 285
|
512 |
+
},
|
513 |
+
{
|
514 |
+
"epoch": 0.7717897538256819,
|
515 |
+
"grad_norm": 54201.045662727825,
|
516 |
+
"learning_rate": 2.978543222347076e-06,
|
517 |
+
"loss": 20.7529,
|
518 |
+
"mean_token_accuracy": 0.4138728640973568,
|
519 |
+
"step": 290
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.7850964737192282,
|
523 |
+
"grad_norm": 23857.53870983074,
|
524 |
+
"learning_rate": 2.6544023772782736e-06,
|
525 |
+
"loss": 21.3047,
|
526 |
+
"mean_token_accuracy": 0.403152472525835,
|
527 |
+
"step": 295
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.7984031936127745,
|
531 |
+
"grad_norm": 11423.97832396548,
|
532 |
+
"learning_rate": 2.346217694934847e-06,
|
533 |
+
"loss": 20.4021,
|
534 |
+
"mean_token_accuracy": 0.41206730976700784,
|
535 |
+
"step": 300
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 0.7984031936127745,
|
539 |
+
"eval_loss": 3.0904834270477295,
|
540 |
+
"eval_mean_token_accuracy": 0.34269434379206765,
|
541 |
+
"eval_runtime": 42.4109,
|
542 |
+
"eval_samples_per_second": 3.395,
|
543 |
+
"eval_steps_per_second": 0.424,
|
544 |
+
"step": 300
|
545 |
+
},
|
546 |
+
{
|
547 |
+
"epoch": 0.8117099135063207,
|
548 |
+
"grad_norm": 6555.658931606807,
|
549 |
+
"learning_rate": 2.0546586164151827e-06,
|
550 |
+
"loss": 19.3343,
|
551 |
+
"mean_token_accuracy": 0.42890567928552625,
|
552 |
+
"step": 305
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 0.825016633399867,
|
556 |
+
"grad_norm": 8596.180267406271,
|
557 |
+
"learning_rate": 1.7803584685552877e-06,
|
558 |
+
"loss": 19.1283,
|
559 |
+
"mean_token_accuracy": 0.4296626977622509,
|
560 |
+
"step": 310
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 0.8383233532934131,
|
564 |
+
"grad_norm": 7559.729843914057,
|
565 |
+
"learning_rate": 1.523913088211415e-06,
|
566 |
+
"loss": 19.9312,
|
567 |
+
"mean_token_accuracy": 0.4130441091954708,
|
568 |
+
"step": 315
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 0.8516300731869594,
|
572 |
+
"grad_norm": 6283.0641437588,
|
573 |
+
"learning_rate": 1.2858795279787517e-06,
|
574 |
+
"loss": 20.0128,
|
575 |
+
"mean_token_accuracy": 0.40999465957283976,
|
576 |
+
"step": 320
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.8649367930805056,
|
580 |
+
"grad_norm": 4627.199331551124,
|
581 |
+
"learning_rate": 1.0667748461575544e-06,
|
582 |
+
"loss": 20.2021,
|
583 |
+
"mean_token_accuracy": 0.40563797727227213,
|
584 |
+
"step": 325
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.8782435129740519,
|
588 |
+
"grad_norm": 3896.885861785845,
|
589 |
+
"learning_rate": 8.670749835951964e-07,
|
590 |
+
"loss": 20.3633,
|
591 |
+
"mean_token_accuracy": 0.40211157202720643,
|
592 |
+
"step": 330
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 0.8915502328675982,
|
596 |
+
"grad_norm": 3649.4556728802945,
|
597 |
+
"learning_rate": 6.872137298438653e-07,
|
598 |
+
"loss": 20.6856,
|
599 |
+
"mean_token_accuracy": 0.39633470848202706,
|
600 |
+
"step": 335
|
601 |
+
},
|
602 |
+
{
|
603 |
+
"epoch": 0.9048569527611444,
|
604 |
+
"grad_norm": 5894.774814516487,
|
605 |
+
"learning_rate": 5.275817808796013e-07,
|
606 |
+
"loss": 21.1202,
|
607 |
+
"mean_token_accuracy": 0.38578067943453787,
|
608 |
+
"step": 340
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.9181636726546906,
|
612 |
+
"grad_norm": 4756.426577271269,
|
613 |
+
"learning_rate": 3.885258904295575e-07,
|
614 |
+
"loss": 21.8543,
|
615 |
+
"mean_token_accuracy": 0.37522283270955087,
|
616 |
+
"step": 345
|
617 |
+
},
|
618 |
+
{
|
619 |
+
"epoch": 0.9314703925482368,
|
620 |
+
"grad_norm": 11889.44146408838,
|
621 |
+
"learning_rate": 2.703481167509281e-07,
|
622 |
+
"loss": 22.5845,
|
623 |
+
"mean_token_accuracy": 0.36378281489014624,
|
624 |
+
"step": 350
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 0.9314703925482368,
|
628 |
+
"eval_loss": 3.6812663078308105,
|
629 |
+
"eval_mean_token_accuracy": 0.2753951284620497,
|
630 |
+
"eval_runtime": 42.3376,
|
631 |
+
"eval_samples_per_second": 3.401,
|
632 |
+
"eval_steps_per_second": 0.425,
|
633 |
+
"step": 350
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.9447771124417831,
|
637 |
+
"grad_norm": 6803.573866074052,
|
638 |
+
"learning_rate": 1.73305166497707e-07,
|
639 |
+
"loss": 22.5139,
|
640 |
+
"mean_token_accuracy": 0.36300976797938345,
|
641 |
+
"step": 355
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.9580838323353293,
|
645 |
+
"grad_norm": 7457.921947626093,
|
646 |
+
"learning_rate": 9.760783710056176e-08,
|
647 |
+
"loss": 22.5036,
|
648 |
+
"mean_token_accuracy": 0.3649313189089298,
|
649 |
+
"step": 360
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 0.9713905522288756,
|
653 |
+
"grad_norm": 8489.33440106548,
|
654 |
+
"learning_rate": 4.3420558871060116e-08,
|
655 |
+
"loss": 22.7636,
|
656 |
+
"mean_token_accuracy": 0.35811431556940077,
|
657 |
+
"step": 365
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.9846972721224219,
|
661 |
+
"grad_norm": 10404.8253118789,
|
662 |
+
"learning_rate": 1.0861037824896337e-08,
|
663 |
+
"loss": 22.8268,
|
664 |
+
"mean_token_accuracy": 0.3570818044245243,
|
665 |
+
"step": 370
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 0.998003992015968,
|
669 |
+
"grad_norm": 7227.984198697766,
|
670 |
+
"learning_rate": 0.0,
|
671 |
+
"loss": 22.9385,
|
672 |
+
"mean_token_accuracy": 0.3560729533433914,
|
673 |
+
"step": 375
|
674 |
+
},
|
675 |
+
{
|
676 |
+
"epoch": 0.998003992015968,
|
677 |
+
"step": 375,
|
678 |
+
"total_flos": 3.616227566899167e+18,
|
679 |
+
"train_loss": 16.595592213948567,
|
680 |
+
"train_runtime": 29081.677,
|
681 |
+
"train_samples_per_second": 0.827,
|
682 |
+
"train_steps_per_second": 0.013
|
683 |
+
}
|
684 |
+
],
|
685 |
+
"logging_steps": 5,
|
686 |
+
"max_steps": 375,
|
687 |
+
"num_input_tokens_seen": 0,
|
688 |
+
"num_train_epochs": 1,
|
689 |
+
"save_steps": 500,
|
690 |
+
"stateful_callbacks": {
|
691 |
+
"TrainerControl": {
|
692 |
+
"args": {
|
693 |
+
"should_epoch_stop": false,
|
694 |
+
"should_evaluate": false,
|
695 |
+
"should_log": false,
|
696 |
+
"should_save": false,
|
697 |
+
"should_training_stop": false
|
698 |
+
},
|
699 |
+
"attributes": {}
|
700 |
+
}
|
701 |
+
},
|
702 |
+
"total_flos": 3.616227566899167e+18,
|
703 |
+
"train_batch_size": 2,
|
704 |
+
"trial_name": null,
|
705 |
+
"trial_params": null
|
706 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbe9478d8f56b22912ff9b43a0ccc0520a1d9f8aa69517ceb37f58ab500290ce
|
3 |
+
size 7288
|